Design of Energy-efficient Hierarchical Scheduling for Integrated Modular Avionics Systems

Recently the integrated modular avionics (IMA) architecture which introduces the concept of resource partitions becomes popular as an alternative to the traditional federated architecture. This study investigates the problem of designing hierarchical scheduling for IMA systems. The proposed scheduler model enables strong temporal partitioning, so that multiple hard real-time applications can be easily integrated into an uniprocessor platform. This paper derives the mathematic relationships among partition cycle, partition capacity and schedulability under the real-time condition, and then proposes an algorithm for optimizing partition parameters. Real-time tasks with arbitrary deadlines are considered for generality. To further improve the basic algorithm and reduce the energy consumption for embedded systems in aircraft, a power optimization approach is also proposed by exploiting the slack time. Experimental results show that the designed system can guarantee the hard real-time requirement and reduce the power consumption by at least 14%.